With the advance of smartphones, wearables devices, and other Internet of Things devices, there is a variety of sensors that are generating time-series measurements of your daily activity. These sensors allow the emergence of new services that are beneficial to several areas including health monitoring, safety, and productivity. While cameras, microphones, and the location are preserved as privacy-sensitive, the privacy implication of activity recognition sensors is still underestimated. In fact, the detailed time-series user data shared with untrusted third parties could be used to infer private and sensitive information user information (e.g. if the user is smoking).

This project will focus on the Privacy-Utility Trade-off (PUT) in time-series data (specifically activity monitoring data). At the beginning, I will be investigating on a method to encrypt the user private data using adversarial learning. Then, I will investigate on the accuracy of the sensitive information’s inference using two or more time-correlated signals which have been transformed individually and independently of the one another’s.

• data processing
• machine learning
• GAN
• data privacy